AIML - Machine Learning Engineering, Machine Learning Platform and Infrastructure
Description For AIML - Machine Learning Engineering, Machine Learning Platform and Infrastructure
Join Apple's Foundation Model Services team within the Machine Learning Platform Technologies organization, the backbone of Apple Intelligence. We build frameworks, services, and tools that power Apple's largest foundation models on servers. Our infrastructure supports crucial services including Apple Search, Apple Music, AppleTV, AppStore, iMessages, Photos & Camera, Spotlight, Safari, Siri, and upcoming products, serving millions of queries daily with incredibly low latencies.
As a Machine Learning Engineer, you'll work on optimizing billions of parameter language, vision, and speech models using state-of-the-art technologies at Apple's scale. You'll have the opportunity to impact billions of users worldwide, working with cutting-edge model architectures and high-throughput services at supercomputing scale.
The role involves close collaboration with product teams and the Foundation Model Research team, building production-grade solutions and developing inference capabilities for advanced model architectures. You'll be instrumental in building tools to analyze inference bottlenecks across different hardware configurations and use cases.
We're seeking someone who thinks differently, is eager to break the status quo, and isn't afraid to take risks. You'll be joining a team that values innovation and pushes the boundaries of computing and intelligence. This position offers the chance to mentor other engineers while working on technology that brings smiles to people's faces.
The ideal candidate brings strong expertise in ML technologies, including LLMs, NLP, and Information Retrieval, combined with practical experience in cloud infrastructure and modern programming languages. Your work will directly contribute to Apple's mission of bringing intelligent features to billions of users across their product ecosystem.
Responsibilities For AIML - Machine Learning Engineering, Machine Learning Platform and Infrastructure
- Work closely with product teams to build production grade solutions for serving models to millions of customers in real time
- Collaborate with Foundation Model Research team to prototype and develop inference for cutting edge model architectures
- Build tools to understand bottlenecks in Inference for different hardwares and use cases
- Mentor and guide engineers in the organization
Requirements For AIML - Machine Learning Engineering, Machine Learning Platform and Infrastructure
- 8+ years of experience leading and driving complex, ambiguous projects
- Strong industry background and experience in ML technologies (LLMs, Machine Learning, NLP, Information Retrieval, Statistics)
- Rich experience with high throughput services particularly at supercomputing scale
- Proficient with running applications on Cloud (AWS / Azure or equivalent) using Kubernetes, Docker etc
- Proficient in building and maintaining systems written in modern languages (eg: Golang, python)
- Familiar with one of the popular ML Frameworks like Pytorch, Tensorflow
- Familiar with fundamental Deep Learning architectures such as Transformers, Encoder/Decoder models
- Familiarity with Nvidia TensorRT-LLM, vLLLM, DeepSpeed, Nvidia Triton Server etc
